rdna3 repositories
Trending repositories tagged rdna3, ranked by trending score. Updated daily.
-
1
stew675/llama-cpp-rdna-boosts
A set of performant RDNA/HIP patches against llama.cpp focusing on high speed inferencing with numerics assurance
GitHub · Shell · 273 stars · 24 forks · +6 stars in 24 hours · Trending score 1.86
-
2
SnowLLM/SnowLLM
Your Ryzen AI Max is running at half speed. SnowLLM: up to 9x faster prefill and 2x faster decode than llama.cpp on the same GGUF. Qwen3.6-35B-A3B, Qwen3.8-Flash-Next, DeepSeek-V4-Flash.
GitHub · Python · 21 stars · 2 forks · +6 stars in 24 hours · Trending score 1.48
-
3
zolotukhin/zinc
Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon
GitHub · Zig · 532 stars · 39 forks · +1 stars in 24 hours · Trending score 1.05
-
4
Helemen7/RedNavi
Native macOS driver for AMD RDNA 3 GPUs (Navi 32 RX 7800 XT first): display, Vulkan (RADV) and Metal. Research prototype, contributors welcome.
GitHub · C · 28 stars · 6 forks · 0 stars in 24 hours · Trending score 0.59
-
5
countervolts/d4r
NVIDIA's official DLSS 3/4/4.5 and DLSS MFG on AMD RDNA2/3/4 GPUs on Windows and Linux.
GitHub · C++ · 350 stars · 11 forks · 0 stars in 24 hours · Trending score 0.57
-
6
zgauthier2000/fsr4-shader-performance-overrides
Faster FSR 4.1.2 upscaling on Radeon RX 6000 and RX 7000 graphics cards, on Windows and Linux: drop-in DLLs and shader overrides. Exact version keeps AMD's picture byte for byte; optional lossy version is faster still.
GitHub · C · 367 stars · 6 forks · 0 stars in 24 hours · Trending score 0.51
-
7
ddk103/strata-ddkRDNA3
Measured RDNA3 (RX 7900 XTX / gfx1100) tuning for Strata + Qwen3.8-Flash-Next MoE: verified launch flags, corrected third-party claims, two reproducible upstream bugs, and a 16-run quantization study. 中文文档见 README.zh-CN.md
GitHub · C++ · 7 stars · 1 forks · +1 stars in 24 hours · Trending score 0.41
-
8
leolivm/vermilion
Experimental macOS Tahoe driver for the AMD Radeon RX 7900 XT (Navi 31 / RDNA3): acceleration, high refresh, multi-monitor
GitHub · Rust · 8 stars · 0 forks · 0 stars in 24 hours · Trending score 0.31
-
9
countervolts/x4r
Intel XeSS XMX kernels translated to run on AMD RDNA3/RDNA4 WMMA under Linux/Proton.
GitHub · C++ · 13 stars · 0 forks · 0 stars in 24 hours · Trending score 0.28
-
10
OpenNeuralRendering/OpenRR
Clean-room port of NVIDIA DLSS Ray Reconstruction for RDNA3/3.5/4 GPUs, for D3D12 and Vulkan games. MIT. https://ko-fi.com/proceduralnilo
GitHub · C++ · 9 stars · 1 forks · 0 stars in 24 hours · Trending score 0.27
-
11
mehbul/strata
Run 35B mixture-of-experts LLMs on a 16 GB AMD Radeon GPU. A Rust inference engine for ROCm on Windows: reads the GGUF, solves weight placement across VRAM and system RAM, tunes by measurement, compacts context, and serves an OpenAI-compatible API with a web console. No Ollama, no daemon.
GitHub · Rust · 7 stars · 2 forks · 0 stars in 24 hours · Trending score 0.08
-
12
Cedriceuh/freetoken-rdna3
Fast local LLM inference on AMD Radeon RX 7900 XTX / XT (RDNA3, ROCm): big Mixture-of-Experts models like Qwen3.8-Flash-Next on one or two consumer GPUs. Up to 4 parallel agents with 262k context each, or one 1M-token context, OpenAI/Anthropic API, NVFP4 and EXL3 checkpoints. A tuned build of FreeToken.
GitHub · Python · 12 stars · 0 forks · 0 stars in 24 hours · Trending score 0.07
-
13
Mateusz-Dera/ROCm-AI-Installer
Installation script for an AI applications using ROCm on Linux.
GitHub · Shell · 51 stars · 8 forks · 0 stars in 24 hours · Trending score 0.00
-
14
GPUOpen-Tools/isa_spec_manager
Utilities for accessing AMD's Machine-Readable GPU ISA Specifications.
GitHub · C++ · 57 stars · 5 forks · 0 stars in 24 hours · Trending score 0.00
-
15
Heretek-AI/homebrew-tap
⚡ Zero-dependency Homebrew tap for high-performance LLMs (CachyLLama, ROCmFPX, llama-ai). Optimized for AMD ROCm 7 (Strix Halo, RDNA3/4), Apple Silicon Metal, & Vulkan RADV.
GitHub · Ruby · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
16
luuumi-dev/nullarc
nullarc — Metal on AMD Radeon 780M for macOS Tahoe: GPU bring-up, WindowServer compositing at 120 Hz, Metal over Vulkan (Mesa RADV)
GitHub · C · 53 stars · 8 forks · 0 stars in 24 hours · Trending score 0.00